Underwater Target Detection Lightweight Algorithm Based on Multi-Scale Feature Fusion

被引:14
|
作者
Chen, Liang [1 ]
Yang, Yuyi [1 ]
Wang, Zhenheng [1 ]
Zhang, Jian [1 ]
Zhou, Shaowu [1 ]
Wu, Lianghong [1 ]
机构
[1] Hunan Univ Sci & Technol, Sch Informat & Elect Engn, Xiangtan 411201, Peoples R China
基金
中国国家自然科学基金;
关键词
underwater target detection; multi-scale fusion; transformer; YOLOv5; lightweight;
D O I
10.3390/jmse11020320
中图分类号
U6 [水路运输]; P75 [海洋工程];
学科分类号
0814 ; 081505 ; 0824 ; 082401 ;
摘要
The performance of underwater target detection algorithms is affected by poor imaging quality in underwater environments. Due to the arithmetic power limitation of underwater devices, existing deep learning networks are unable to provide efficient detection processes with high detection accuracy. Lightweight CNN models have been actively applied for underwater environment detection, yet their lite feature fusion networks cannot provide effective fusion effects and reduce the detection accuracy. In this paper, a lightweight algorithm based on multi-scale feature fusion was proposed, with the model parameters greatly reduced, improving the target detection accuracy. The forward propagation memory overhead is reduced by using multi-scale shared convolutional kernels and pooling operations to co-construct the query matrix in the Tansformer encoding stage. Then, the feature fusion path is optimized in order to enhance the connection of multi-scale features. A multiscale feature adaptive fusion strategy is used to enhance the detection performance and reduce the dependence on the complex feature extraction network. The feature extraction network is also reparameterized to simplify the operation. Using the UPRC offshore dataset for validation, the study results have demonstrated that the statistical mAP metrics validate the detection accuracy. Compared with SSD, RetinaNet and YOLOv5-s improved by 13%, 8.6%, and 0.8%, while the number of parameters decreased by 76.09%, 89.74%, and 87.67%. In addition, compared with the YOLOv5-lite model algorithm with the same parameter volume, the mAP is improved by 3.8%, which verifies the accuracy and efficiency of the algorithm in this paper.
引用
收藏
页数:17
相关论文
共 50 条
  • [21] Pedestrian detection algorithm based on multi-scale feature extraction and attention feature fusion
    Xia, Hao
    Ma, Jun
    Ou, Jiayu
    Lv, Xinyao
    Bai, Chengjie
    DIGITAL SIGNAL PROCESSING, 2022, 121
  • [22] Underwater target detection algorithm based on feature enhancement and feature fusion
    Liu, Qinxiao
    Ji, Longlong
    Zhao, Fen
    ENGINEERING RESEARCH EXPRESS, 2025, 7 (01):
  • [23] A Lightweight Road Defect Detection Method Based on Multi-scale Hybrid Feature Fusion
    Kuang, Jin
    Liu, Dong
    Lv, Hong
    Xu, Xinyue
    Zhang, Lingrong
    THIRTEENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2021), 2022, 12083
  • [24] Insulator Defect Detection Based on Lightweight Network and Enhanced Multi-scale Feature Fusion
    Chen K.
    Liu X.
    Jia L.
    Fang Y.
    Zhao C.
    Gaodianya Jishu/High Voltage Engineering, 2024, 50 (03): : 1289 - 1301
  • [25] Lightweight Small Target Detection Algorithm with Multi-Feature Fusion
    Yang, Rujin
    Zhang, Jingwei
    Shang, Xinna
    Li, Wenfa
    ELECTRONICS, 2023, 12 (12)
  • [26] Underwater Target Detection Algorithm Based on Feature Fusion Enhancement
    Chen, Liang
    Yin, Tao
    Zhou, Shaowu
    Yi, Guo
    Fan, Di
    Zhao, Jin
    ELECTRONICS, 2023, 12 (13)
  • [27] Fan Blade Crack Detection Algorithm Based on Multi-Scale Feature Fusion
    Qi, Yongjun
    Tang, Hailin
    Khuder, Altangerel
    IEEE ACCESS, 2025, 13 : 15762 - 15772
  • [28] A Lightweight YOLO Object Detection Algorithm Based on Bidirectional Multi-Scale Feature Enhancement
    Liu, Qunpo
    Zhang, Jingwen
    Zhang, Zhuoran
    Bu, Xuhui
    Hanajima, Naohiko
    ADVANCED THEORY AND SIMULATIONS, 2024, 7 (05)
  • [29] Small target detection algorithm for printing defects detection based on context structure perception and multi-scale feature fusion
    Wenqian Chen
    Yuanlin Zheng
    Kaiyang Liao
    Haiwen Liu
    Yalin Miao
    Bangyong Sun
    Signal, Image and Video Processing, 2024, 18 : 657 - 667
  • [30] Small target detection algorithm for printing defects detection based on context structure perception and multi-scale feature fusion
    Chen, Wenqian
    Zheng, Yuanlin
    Liao, Kaiyang
    Liu, Haiwen
    Miao, Yalin
    Sun, Bangyong
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (01) : 657 - 667